© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24092
    Prev
    Next
    INDEX
    Explanations

    Document beginnings/introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åıĺæĢģ
    -0.27
    çĵ·
    -0.26
    婵
    -0.25
    кÑĤ
    -0.25
    éĿĻæĢģ
    -0.25
    æĪijåİ»
    -0.25
    omy
    -0.25
    润
    -0.24
    ^^^^
    -0.24
    ç°ª
    -0.24
    POSITIVE LOGITS
    æł·
    0.27
    istingu
    0.26
    æ²½
    0.26
     defensively
    0.25
     Scroll
    0.25
    -awesome
    0.25
    çī¹èī²
    0.24
    -prom
    0.24
     exem
    0.24
    SY
    0.24
    Activations Density 0.001%

    No Known Activations